• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.326-328
• /
• 2000

인공신경회로망 기술은 선형 또는 비선형성 계산 문제를 복잡도에 무관하게 학습에 의해 자동으로 근사한다. 또한 알고리즘이 단순하며 잡음에 강하여 다양한 분야에 적용되고 있다. 반면 대상시스템의 특성이나 조건이 변경되면 계산성능을 보장할 수 없고, 계산의 신뢰성 보장 한계가 모호하기 때문에 제어문제에는 실용화가 어려운 것으로 알려져 있다. 제안 모델은 인공신경회로망의 장점을 유지하면서, 위와 같은 문제점을 해결한다. 시뮬레이션을 통하여 제안 모델은 기존 제어기에 비해 우수한 추종제어성능을 보이는 것으로 밝혀졌다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.352-360
• /
• 2002

본 논문에서는 미세 거리변와에 따른 자기자화의 변화를 구현하는데 있어 비선형적인 요소를 포함하고 있어 이를 수학적으로 모델링하여 제어기를 설계하는데는 많은 난점을 내포하고 있다. 따라서 거리변화에 따른 자기장의 비선형적인 변화 관계를 신경회로망 제어기의 학습을 통하여 제어할 수 있도록 신경 회로망 제어기를 제안하려 한다.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.361-363
• /
• 2004

시간 및 주파수 특성 분석이 용이한 웨이블릿을 신경회로망에 적용시킨 웨이블릿 신경 회로망의 파라미터 학습 방법에는 오차 역전파 알고리듬 및 유선 알고리듬 등 여러 가지 방법이 있으나 이러한 학습 방법들은 수렴 시간이 오래 걸리는 단점을 가진다. 따라서 본 논문에서는 웨이블릿 신경 회로망의 최적 파라미터를 결정하기 위한 학습 방법으로 일반적으로 비선형 시스템 추정에 주로 사용되는 확장 칼만 필터 알고리듬을 적용한 신경회로망을 제안한다. 또한 제안된 학습 알고리듬을 이용한 웨이블릿 신경 회로망으로 간접 적응 제어기를 설계하여 연속 시간 혼돈 시스템인 Duffing 시스템의 제어에 적용함으로써 확장 칼만 필터 학습 알고리듬을 적용한 웨이블릿 신경 회로망 모델의 우수성을 보인다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.41-48
• /
• 2003

This paper presents an indirect adaptive neuro controller using modified chaotic neural networks(MCNN) for nonlinear dynamic system. A modified chaotic neural networks model is presented for simplifying the traditional chaotic neural networks and enforcing dynamic characteristics. A new Dynamic Backpropagation learning method is also developed. The proposed MCNN paradigm is applied to the system identification of a MIMO system and the indirect adaptive neuro controller. The simulation results show good performances, since the MCNN has robust adaptability to nonlinear dynamic system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.383-388
• /
• 1999

In this paper, we propose the fuzzy-neural controller with genetic algorithm(GA) for precise on-line control. We design the proposed controller having a ability to adjust membership function for a plant by advanced algorithm of fuzzy-neural network after approximative one being completed by genetic algorithm. Finally we compare the result for a speed control of DC servo motor by the proposed controller with GA-fuzzy one in order to evaluate its performance and precision.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.12 no.3
• /
• pp.139-146
• /
• 1998

In this paper, we proposed the hybrid intelligent control method for fast response time and precise speed control of the AC Servo system. The proposed system first used the fuzzy-neural network control methods for fast response time and when the error reaches the preset value, used the PLL control method. In order to verify the advantage of he proposed method, the system is implemented. The results of the simulation and the experiment of speed control to use the 3-phase induction motor as a plant, we verified excellency of the proposed control method to compare with the conventional fuzzy-neural network control method.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.2 s.314
• /
• pp.24-31
• /
• 2007

This paper presents self tuning PI(STPI) controller of IPMSM drive using neural network. In general, PI controller in computer numerically controlled machine process fixed gain. They may perform well under some operating conditions, but not all. To increase the robustness of fixed gain PI controller, STPI controller proposes a new method based neural network. STPI controller is developed to minimize overshoot, rise time and settling time following sudden parameter changes such as speed, load torque and inertia. Also, this paper is proposed speed control of IPMSM using neural network and estimation of speed using artificial neural network(ANN) controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The results on a speed controller of IPMSM are presented to show the effectiveness of the proposed gain tuner. And this controller is better than the fixed gains one in terms of robustness, even under great variations of operating conditions and load disturbance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.1811-1817
• /
• 2014

In this paper, a PID controller with interpolated gains by use of neural networks is proposed for the formation control problem that following robots track a leading robot with constant distances and angles when there are changes in the mass of the following robot. The whole control system is composed of a kinematic controller and a dynamic controller considering the robot dynamics. The dynamic controller is the PID controller with varying gains, and the proper gains are obtained for some representative masses of the follower robot by the genetic algorithm. Neural networks is trained using the genetic algorithm with the gain data obtained in the previous step. The trained neural network determines optimal PID gains for a random mass of following robot. Simulation studies show that for arbitrary masses of the tracking robot, the PID controller with interpolated gains by the trained neural network has better tracking performance than that of the PID controller with fixed gains.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.1
• /
• pp.30-37
• /
• 2000

We studied on acquiring of transfer function and tuning of 2-DOF PID controller using ANFIS for the optimum control to turbine's variables variety. Since the shape of a membership function in the ANFIS based on the characteristics of plant. ANFIS based control method is effective for plant that its variable vary. On the other hand, a start-up time is very short and its variable's value for optimal start-up in gas turbine should be varied, but it is very difficult for such a controller to design. In this paper, we tune 2-DOF PID controller after apply a ANFIS to the operating data of Gun-san gas turbine and verify the characteristics. Its results is compared to the conventional PID controller and discuss. We expect this method will be used for another process because it is studied on the real operating data.

• Journal of Navigation and Port Research
• /
• v.26 no.5
• /
• pp.537-542
• /
• 2002

Recently, an automatic crane control system is required with high speed and rapid transportation. Therefore, when container is transferred from th intial coordinate to the finial coordinate, the container paths should be built in terms of the least time and no swing. So in this paper, we calculated the anti-collision path for avoiding collision in its movement to the finial coordinate. And we constructed the neural network predictive PID (NNPPID) controller to control the precise navigation. The proposed predictive control system is composed of the neural network predictor, PID controller, neural network self-tuner which yields parameters of PID. Analyzed crane system through simulation, and proved excellency of control performance than other conventional controllers.